Machinelearning – Telegram
384K subscribers
4.46K photos
863 videos
17 files
4.9K links
Погружаемся в машинное обучение и Data Science

Показываем как запускать любые LLm на пальцах.

По всем вопросам - @haarrp

@itchannels_telegram -🔥best channels

Реестр РКН: clck.ru/3Fmqri
Download Telegram
Layerwise learning for Quantum Neural Networks

Training strategy that addresses vanishing gradients in quantum neural networks (QNNs).

https://blog.tensorflow.org/2020/08/layerwise-learning-for-quantum-neural-networks.html

Quirk: a drag-and-drop quantum circuit simulator with nice visualizations: https://algassert.com/quirk

Paper: https://arxiv.org/abs/2003.02989

Quantum Intuition:https://www.youtube.com/channel/UC-2knDbf4kzT3uzWo7iTJyw

@ai_machinelearning_big_data
👍1
Guided Collaborative Training for Pixel-wise Semi-Supervised Learning

Github: https://github.com/ZHKKKe/PixelSSL

Paper: https://arxiv.org/abs/2008.05258

@ai_machinelearning_big_data
🔥 Language Interpretability Tool

Open-source platform for visualization and understanding of NLP models.

Github: https://github.com/PAIR-code/lit

Developer Guide: https://github.com/PAIR-code/lit/blob/main/docs/development.md

Paper: https://arxiv.org/abs/2008.05122

Video: https://www.youtube.com/watch?v=j0OfBWFUqIE

@ai_machinelearning_big_data
This media is not supported in your browser
VIEW IN TELEGRAM
The Hessian Penalty — Official Implementation

It efficiently optimizes the Hessian of your neural network to be diagonal in an input, leading to disentanglement in that input.

https://www.wpeebles.com/hessian-penalty

Github: https://github.com/wpeebles/hessian_penalty

Paper: https://arxiv.org/abs/2008.10599

Video: https://www.youtube.com/watch?v=uZyIcTkSSXA&feature=youtu.be

@ai_machinelearning_big_data